Training in progress, step 15

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e94ac18ccd339ad4da795bb8b104076dea151fb4c35cf06cc744458d92f92f8
+oid sha256:354d9bc55a0da441ec464af2662101a8a5bcd9e1eb41e440f429de75a19f8b07
 size 42002136

logging.jsonl

@@ -9,3 +9,11 @@
 {"loss": 2.26151538, "token_acc": 0.50835322, "grad_norm": 0.85837853, "learning_rate": 7.297e-05, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.608553, "epoch": 0.07317073, "global_step/max_steps": "9/369", "percentage": "2.44%", "elapsed_time": "9s", "remaining_time": "6m 6s"}
 {"loss": 2.15133929, "token_acc": 0.55084746, "grad_norm": 1.18577528, "learning_rate": 8.108e-05, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.634457, "epoch": 0.08130081, "global_step/max_steps": "10/369", "percentage": "2.71%", "elapsed_time": "10s", "remaining_time": "6m 4s"}
 {"loss": 1.63149965, "token_acc": 0.62237762, "grad_norm": 0.70675153, "learning_rate": 8.919e-05, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.650612, "epoch": 0.08943089, "global_step/max_steps": "11/369", "percentage": "2.98%", "elapsed_time": "11s", "remaining_time": "6m 7s"}
+{"loss": 1.6930747, "token_acc": 0.64858491, "grad_norm": 0.75992346, "learning_rate": 9.73e-05, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.671389, "epoch": 0.09756098, "global_step/max_steps": "12/369", "percentage": "3.25%", "elapsed_time": "12s", "remaining_time": "6m 4s"}
+{"loss": 2.18108296, "token_acc": 0.58454106, "grad_norm": 1.50389647, "learning_rate": 0.00010541, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.689945, "epoch": 0.10569106, "global_step/max_steps": "13/369", "percentage": "3.52%", "elapsed_time": "13s", "remaining_time": "6m 2s"}
+{"loss": 1.73638082, "token_acc": 0.6183953, "grad_norm": 0.59281182, "learning_rate": 0.00011351, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.707752, "epoch": 0.11382114, "global_step/max_steps": "14/369", "percentage": "3.79%", "elapsed_time": "14s", "remaining_time": "5m 59s"}
+{"loss": 1.89742863, "token_acc": 0.53033268, "grad_norm": 0.60121316, "learning_rate": 0.00012162, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.724128, "epoch": 0.12195122, "global_step/max_steps": "15/369", "percentage": "4.07%", "elapsed_time": "15s", "remaining_time": "5m 56s"}
+{"loss": 1.58984172, "token_acc": 0.58458244, "grad_norm": 1.01862383, "learning_rate": 0.00012973, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.722935, "epoch": 0.1300813, "global_step/max_steps": "16/369", "percentage": "4.34%", "elapsed_time": "16s", "remaining_time": "6m 4s"}
+{"loss": 1.72712588, "token_acc": 0.57186544, "grad_norm": 1.11258352, "learning_rate": 0.00013784, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.737209, "epoch": 0.13821138, "global_step/max_steps": "17/369", "percentage": "4.61%", "elapsed_time": "17s", "remaining_time": "6m 1s"}
+{"loss": 1.48443031, "token_acc": 0.67521368, "grad_norm": 0.99743199, "learning_rate": 0.00014595, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.750267, "epoch": 0.14634146, "global_step/max_steps": "18/369", "percentage": "4.88%", "elapsed_time": "18s", "remaining_time": "5m 58s"}
+{"loss": 1.01479948, "token_acc": 0.77894737, "grad_norm": 0.84560066, "learning_rate": 0.00015405, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.76235, "epoch": 0.15447154, "global_step/max_steps": "19/369", "percentage": "5.15%", "elapsed_time": "19s", "remaining_time": "5m 55s"}